{"id":"https://openalex.org/W4391020081","doi":"https://doi.org/10.1109/cdc49753.2023.10383316","title":"Adaptive Optimal Control of Nonlinear Systems with Multiple Time-Scale Eligibility Traces","display_name":"Adaptive Optimal Control of Nonlinear Systems with Multiple Time-Scale Eligibility Traces","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391020081","doi":"https://doi.org/10.1109/cdc49753.2023.10383316"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383316","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018604914","display_name":"Jun Rao","orcid":"https://orcid.org/0000-0002-7467-4898"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Rao","raw_affiliation_strings":["Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777024","display_name":"Jingcheng Wang","orcid":"https://orcid.org/0000-0002-4277-1263"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingcheng Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058905701","display_name":"Jiahui Xu","orcid":"https://orcid.org/0000-0002-4058-0447"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087893108","display_name":"Shunyu Wu","orcid":"https://orcid.org/0000-0001-9856-2148"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunyu Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Key Laboratory of System Control and Information Processing,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2609998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2258","last_page":"2263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9638000130653381,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12047","display_name":"Viral Infections and Vectors","score":0.9520999789237976,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6855688095092773},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5880043506622314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5748413801193237},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.4573570489883423},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4528118968009949},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4359779953956604},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4325752556324005},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4233381152153015},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4124767780303955},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39937669038772583},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28825536370277405},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15571847558021545}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6855688095092773},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5880043506622314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5748413801193237},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.4573570489883423},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4528118968009949},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4359779953956604},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4325752556324005},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4233381152153015},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4124767780303955},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39937669038772583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28825536370277405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15571847558021545},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383316","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.5600000023841858,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G4341435642","display_name":null,"funder_award_id":"62273234","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2024303516","https://openalex.org/W2098035803","https://openalex.org/W2099836790","https://openalex.org/W2156629001","https://openalex.org/W2568019971","https://openalex.org/W2614992370","https://openalex.org/W2770173563","https://openalex.org/W2949510088","https://openalex.org/W2992511782","https://openalex.org/W3081393816","https://openalex.org/W3097662863","https://openalex.org/W3100789280","https://openalex.org/W3114263192","https://openalex.org/W3135419645","https://openalex.org/W3173852058","https://openalex.org/W3180181113","https://openalex.org/W3214815869","https://openalex.org/W4214717370","https://openalex.org/W4280597130","https://openalex.org/W4280607589","https://openalex.org/W4285585243","https://openalex.org/W4313364788","https://openalex.org/W6746638498"],"related_works":["https://openalex.org/W2061122711","https://openalex.org/W4247954915","https://openalex.org/W2131958170","https://openalex.org/W2273754158","https://openalex.org/W2336747664","https://openalex.org/W2357130048","https://openalex.org/W4206605161","https://openalex.org/W1745811811","https://openalex.org/W2136715810","https://openalex.org/W2090412404"],"abstract_inverted_index":{"Adaptive":[0],"dynamic":[1],"programming":[2],"(ADP)":[3],"is":[4,41,78,127],"one":[5],"of":[6,16,31,139],"the":[7,12,28,32,36,59,83,97,101,116,131,135,140,146,150,162,169],"main":[8],"methods":[9],"to":[10,26,43,114,129],"solve":[11,58,115],"optimal":[13,102,118,151],"control":[14,98,119],"problem":[15],"nonlinear":[17],"systems.":[18],"Eligibility":[19,75],"traces":[20],"are":[21,112,142,156],"utilized":[22,113],"in":[23,100],"recent":[24],"years":[25],"reduce":[27],"computing":[29],"burden":[30],"value":[33,132,152],"function,":[34],"but":[35],"existing":[37],"fixed":[38],"eligibility":[39],"trace":[40],"difficult":[42],"ensure":[44],"stable":[45],"convergence":[46,136,175],"especially":[47],"when":[48],"facing":[49],"environmental":[50],"changes":[51],"and":[52,90,121,137,154,177],"complex":[53],"neural":[54],"network":[55,148],"structures.":[56],"To":[57],"above":[60],"issues,":[61],"a":[62,122,166,173],"novel":[63],"off-policy":[64],"algorithm,":[65],"<tex":[66,69,104,108],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[67,70,105,109],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$T$</tex>-HDP":[68],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$(\\lambda)$</tex>":[71],"with":[72,161],"Multiple":[73],"Time-scale":[74],"Traces":[76],"(MET),":[77],"proposed.":[79],"By":[80],"utilizing":[81],"MET,":[82],"new":[84,123],"algorithm":[85,141,164,171],"can":[86],"adaptively":[87],"accumulate":[88],"gradients":[89],"include":[91],"more":[92],"gradient":[93],"information,":[94],"which":[95],"guides":[96],"faster":[99,174],"direction.":[103],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$T$</tex>-step":[106],"Truncated":[107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\lambda$</tex>":[110],"-returns":[111],"infinite-horizon":[117],"problems,":[120],"importance":[124],"sampling":[125],"ratio":[126],"designed":[128],"correct":[130],"function.":[133],"Furthermore,":[134],"boundedness":[138],"proved.":[143],"Based":[144],"on":[145],"actor-critic":[147],"architecture,":[149],"function":[153],"policy":[155],"well":[157],"approximated.":[158],"Finally,":[159],"compared":[160],"original":[163],"by":[165],"simulation":[167],"example,":[168],"proposed":[170],"has":[172],"speed":[176],"lower":[178],"variance.":[179]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
